Model comparison
DeepSeek-V3.2-Exp vs ERNIE 5.1
DeepSeek-V3.2-Exp and ERNIE 5.1 score almost the same on the Noometry Index (44.3 vs 43.8), so choose on price, context window or the category you care about most.
Last verified . 18 shared benchmarks.
DeepSeek
BaiduSummary
- They share 18 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 5 categories and ERNIE 5.1 in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.2-Exp leads 51.7 to 41.9.
- The biggest single-benchmark swing is NYT Connections (extended): 36.7% for DeepSeek-V3.2-Exp and 23.4% for ERNIE 5.1.
- DeepSeek-V3.2-Exp has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.2-Exp | ERNIE 5.1 | |
|---|---|---|
| Provider | DeepSeek | Baidu |
| Noometry Index | 44.3 | 43.8 |
| Released | 2025-09-29 | — |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.26 | — |
| Output $ / M tokens | $0.38 | — |
| Results tracked | 49 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 46.5 (#65), ERNIE 5.1: 44.0 (#76)
| Benchmark | DeepSeek-V3.2-Exp | ERNIE 5.1 |
|---|---|---|
| LMArena Coding | 1454 | 1488 |
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| LMArena WebDev | 1362 | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| WeirdML | 39.5% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.2-Exp: 32.7 (#59), ERNIE 5.1: —
| Benchmark | DeepSeek-V3.2-Exp | ERNIE 5.1 |
|---|---|---|
| Terminal-Bench | 39.6% | — |
| APEX-Agents | 21.3% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
| LMArena Search | — | 1227 |
| Vending-Bench 2 | 1,034 | — |
Reasoning Too close to call
DeepSeek-V3.2-Exp: 22.1 (#208), ERNIE 5.1: 21.9 (#211)
| Benchmark | DeepSeek-V3.2-Exp | ERNIE 5.1 |
|---|---|---|
| NYT Connections (extended) | 36.7% | 23.4% |
| LMArena Hard Prompts | 1434 | 1481 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | 52.2% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Chess Puzzles | 14% | — |
| Thematic Generalization | 65% | — |
| DTBench | 87.7% | — |
| LMCA | 29.1% | — |
| Epoch Capabilities Index | 146.27 | — |
Math DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 41.7 (#87), ERNIE 5.1: 40.3 (#92)
| Benchmark | DeepSeek-V3.2-Exp | ERNIE 5.1 |
|---|---|---|
| LMArena Math | 1435 | 1481 |
| MathArena Final-Answer Competitions | 57.7% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 8% | — |
| FrontierMath (Feb 2025 set) | 22.1% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 51.7 (#66), ERNIE 5.1: 41.9 (#102)
| Benchmark | DeepSeek-V3.2-Exp | ERNIE 5.1 |
|---|---|---|
| LMArena Expert | 1436 | 1492 |
| GPQA Diamond | 83.4% | — |
| Vectara Hallucination Rate | 5.3% | — |
Multilingual ERNIE 5.1 leads
DeepSeek-V3.2-Exp: 52.2 (#90), ERNIE 5.1: 55.5 (#29)
| Benchmark | DeepSeek-V3.2-Exp | ERNIE 5.1 |
|---|---|---|
| LMArena Non-English | 1409 | 1454 |
| LMArena Chinese | 1461 | 1508 |
| LMArena French | 1433 | 1488 |
| LMArena German | 1440 | 1470 |
| LMArena Japanese | 1374 | 1422 |
| LMArena Korean | 1371 | 1427 |
| LMArena Russian | 1424 | 1459 |
| LMArena Spanish | 1440 | 1473 |
Instruction Following ERNIE 5.1 leads
DeepSeek-V3.2-Exp: 74.5 (#93), ERNIE 5.1: 76.7 (#37)
| Benchmark | DeepSeek-V3.2-Exp | ERNIE 5.1 |
|---|---|---|
| LMArena Instruction Following | 1413 | 1460 |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#16), ERNIE 5.1: 44.7 (#59)
| Benchmark | DeepSeek-V3.2-Exp | ERNIE 5.1 |
|---|---|---|
| LMArena Longer Query | 1428 | 1462 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference ERNIE 5.1 leads
DeepSeek-V3.2-Exp: 62.4 (#77), ERNIE 5.1: 65.1 (#52)
| Benchmark | DeepSeek-V3.2-Exp | ERNIE 5.1 |
|---|---|---|
| LMArena Text | 1425 | 1468 |
| LMArena Creative Writing | 1403 | 1441 |
| LMArena Multi-Turn | 1427 | 1471 |
| EQ-Bench Creative Writing | 1515 | — |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than ERNIE 5.1?
DeepSeek-V3.2-Exp and ERNIE 5.1 score almost the same on the Noometry Index (44.3 vs 43.8), so choose on price, context window or the category you care about most.
Is DeepSeek-V3.2-Exp or ERNIE 5.1 better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 44.0 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.2-Exp and ERNIE 5.1 share?
18 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and ERNIE 5.1 has 19.